A portable desktop app that drives your logged-in ChatGPT, Claude, Gemini, and Grok side by side through guided workflows. No API keys.
可攜式桌面 app,用引導式流程同時操作你已登入的 ChatGPT、Claude、Gemini、Grok,不需要 API key。
18 public projects from an engineer with twenty years in IT and security who now builds AI agent tooling. Each one has its own page in English and Traditional Chinese, and every page says what doesn't work yet.
18 個公開專案,來自一個做了二十年 IT 與資安、現在專心打造 AI agent 工具的工程師。每個專案都有自己的中英雙語介紹頁,也寫明還做不到的地方。
Code changes. The ideas don't. The heartbeat I learned about in a MUD is what keeps my agents running today.
Code 怎麼變,觀念都不會變。
我在 MUD 學到的心跳,現在用在 agent 上。
Text MUD
I got hooked on a text MUD as a kid and was still playing it in college.
Wizard and sysadmin
While I studied computer science at National Central University in Taiwan, I went from player to wizard, coding for that world and keeping its server running.
Corporate IT
Then I spent nearly twenty years at US companies, working on identity, endpoints, ERP, BI, CRM, and security.
Agents with a heartbeat
Long-running agents need a heartbeat too, a steady tick that keeps the work moving.
文字 MUD
我從小迷上一個文字 MUD,一路玩到大學。
大學當巫師
在中央大學念資工時,我從玩家變成巫師,
幫那個世界寫程式,也顧它的主機。
企業系統
之後在美國將近二十年,
在企業裡做身分管理、端點、
ERP、BI、CRM 和資安。
同樣的心跳
長時間跑的 agent 也要有心跳,
事情才會一直往前走。
Ask ChatGPT, Claude, Gemini, and Grok together and let them check each other, from the desktop, the browser, the terminal, or Claude Code. Plus a companion that remembers your day on your own machine.
讓 ChatGPT、Claude、Gemini、Grok 一起回答、互相檢查,桌面、瀏覽器、終端機或 Claude Code 裡都能用。另外還有一個在你自己電腦上記住一整天的陪伴 app。
A portable desktop app that drives your logged-in ChatGPT, Claude, Gemini, and Grok side by side through guided workflows. No API keys.
可攜式桌面 app,用引導式流程同時操作你已登入的 ChatGPT、Claude、Gemini、Grok,不需要 API key。
A Chrome side panel that turns the AI tabs you already have open into one multi-model workflow.
Chrome 側邊面板,把你已經開著的 AI 分頁串成一條多模型工作流程。
A local workbench that runs staged multi-agent coding workflows on the headless runtimes of Claude Code, Codex, Grok, and Antigravity, with gates and a replayable evidence feed.
本機工作台,在 Claude Code、Codex、Grok、Antigravity 的 headless runtime 上跑分階段的多 agent 工作流程,有關卡,也有可重播的證據紀錄。
A local-first desktop companion that remembers what you worked on, stays quiet most of the time, and cites a source for every answer.
本機優先的桌面陪伴:記得你做過什麼,大部分時間保持安靜,每句回答都附上出處。
A small web app for idea review: pick 5, 12, or 16 rounds, leave, and come back to a Markdown report by link or email.
點子審查的小型網頁 app:選 5、12 或 16 輪,先離開,之後用連結或 email 拿到 Markdown 報告。
A Claude Code skill that puts an idea through a 5, 12, or 16-round review panel before you spend time building it.
Claude Code skill:在你花時間動手之前,先讓點子經過 5、12 或 16 輪的審查。
I start with how a real employee would do the job, and only wake the AI where that person would stop and think.
先想一個真人員工會怎麼做,
只有他得動腦的地方才叫醒 AI。
Open the ERP
An employee opens the ERP to write up a quote.
Plain code
Anything that takes no thinking runs as code: CRUD, search, notifications.
Wake the AI
The AI only wakes up for a judgment call, like how big a discount this customer gets.
Finished in the database
In a 10-step process, maybe 8 steps finish there and only 2 wake the AI.
打開 ERP
員工打開 ERP,要開一張報價單。
走 code
不用動腦的事走 code,
像 CRUD、搜尋、通知。
叫醒 AI
要動腦的才叫醒 AI,
像是這個客戶該給多少折扣。
資料庫做完
10 步的流程,可能 8 步在資料庫做完,
只有 2 步要叫醒 AI。
Connectors, guardrails, memory, and usage tracking for coding agents such as Claude Code, Codex, and OpenClaw.
給 Claude Code、Codex、OpenClaw 這類 coding agent 用的連接器、護欄、記憶與用量追蹤。
An unofficial connector that lets AI agents watch, nudge, and orchestrate Better Agent Terminal sessions, with opt-in tiers and deterministic gates.
非官方連接器,讓 AI agent 查看、推動與調度 Better Agent Terminal 的 session,權限分層、需要主動開啟,並有確定性的關卡。
A server-first cowork workstation: a Paseo-derived daemon with a Better Agent Terminal desktop client. Work in progress, not a release.
伺服器優先的協作工作站:Paseo 衍生的 daemon,加上 Better Agent Terminal 桌面端。仍在開發中,尚未發布。
Tracks Claude Code, Codex, Gemini CLI, and Grok Build token use on your own machine, with a live dashboard and companions that grow with real milestones.
在你自己的電腦上追蹤 Claude Code、Codex、Gemini CLI、Grok Build 的 token 用量,有即時儀表板,陪伴角色會隨真實里程碑成長。
A guarded evolution layer for OpenClaw hosts: Hermes studies and proposes, a Bash watcher guards, and the operator approves.
OpenClaw 主機的守護型演化層:Hermes 研究並提案,Bash watcher 把關,由操作者核准。
A curated operating layer for Claude Code: reviewed specs, persistent memory, reusable skills, and workspaces that follow you across machines.
Claude Code 的精選運作層:經過審閱的規格、持久記憶、可重用的 skill,以及跨機器延續的工作區。
An MCP server for long-term agent memory: decisions, resolved issues, open questions, and knowledge that you can inspect.
給 agent 用的長期記憶 MCP 伺服器:決策、已解決的問題、待回答的問題與知識,都可以檢視。
The main project gets to its first milestone before anything else. New ideas wait their turn, and optimizing comes after it's done.
主專案先做到第一個里程碑,
新想法先排隊,做完再來優化。
Parking Lot
New ideas get written down here. No building, no research, no optimizing.
One main project
Only one at a time, and I stay with it through the boring parts.
First milestone
No new projects until it gets there.
Then optimize
Only finished work gets optimized.
想法停車場
新想法先寫進 Parking Lot,
不做、不研究、不優化。
一個主專案
一次只做一個,
執行期的無聊也接受。
第一個里程碑
做到之前,不開新坑。
再來優化
完成,才有資格優化。
Security checks, machine control, and awareness training that come from running real company systems.
從實際維運公司系統累積出來的資安檢查、機器管控與資安意識教材。
A desktop app and agent skills that run upstream open-source security tools and turn their output into one standardized report.
桌面 app 與 agent skill:執行上游的開源資安工具,把結果整理成一份標準化報告。
An evidence-first control plane for Linux machines that run AI agents and coding tools.
以證據為本的控制平面,管理執行 AI agent 與 coding 工具的 Linux 機器。
A one-page bilingual awareness demo that shows how a look-alike Unicode domain can pass for the real one.
一頁式的中英雙語資安意識示範:看看長得一模一樣的 Unicode 網域,怎麼冒充真的網站。
A parody toy, a strategy notebook, and a helper repository for a community bot.
一個惡搞小玩具、一本策略筆記,還有一個替社群機器人存圖的倉庫。
A bilingual anti-burnout toy: watch four fake AI quota panels burn down, then let golden dragons reset them.
中英雙語的抗倦怠小玩具:看著四個假的 AI 額度面板燒光,再讓黃金龍幫你重置。
Chinese-first notes on Beyblade X: why points, not spin time, decide a match, and how to build a 3v3 deck.
戰鬥陀螺 Beyblade X 中文筆記:為什麼決定勝負的是分數而不是誰轉得最久,以及怎麼配 3v3 牌組。
Image storage for the GitHub issues that the 自由工坊 community bot files from Discord, because Discord attachment links expire.
自由工坊社群機器人從 Discord 開 GitHub issue 時用的圖片倉庫,因為 Discord 附件連結會過期。
I studied computer science at National Central University in Taiwan, then spent nearly two decades in the United States running identity, endpoints, ERP, BI, CRM, and security programs inside real businesses.
我在台灣讀中央大學資工,之後在美國將近二十年,在真實的企業裡負責身分管理、端點、ERP、BI、CRM 與資安計畫。
I build AI agent tooling with the same habits: people keep the final say, state survives a restart, and every claim leaves evidence.
現在我用同樣的習慣做 AI agent 工具:最後的決定權留在人手上,狀態重開也不會遺失,每個說法都留下證據。
Working for months in a real environment matters more than looking clever in a demo.
demo 裡看起來聰明,不如在真實環境裡穩定跑上好幾個月。